3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environmen ....3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environments and open up new possibilities for applications in fields such as virtual reality, architecture, and city planning. The proposed 3D diffusion models will also enhance the accuracy of computer vision tasks related to 3D scene understanding, such as object detection, tracking, and semantic segmentation.Read moreRead less
Using visual science to reduce the dangers of night driving. This project aims to develop novel tests of visual function relevant to the modern night driving environment. Night driving is challenging for all drivers and has been linked to poor visibility under low light conditions. This project will characterise the visual challenges of the modern night driving environment, develop visual tests that incorporate the dynamic light levels typical of night-time roads and assess the association of th ....Using visual science to reduce the dangers of night driving. This project aims to develop novel tests of visual function relevant to the modern night driving environment. Night driving is challenging for all drivers and has been linked to poor visibility under low light conditions. This project will characterise the visual challenges of the modern night driving environment, develop visual tests that incorporate the dynamic light levels typical of night-time roads and assess the association of these tests with night driving performance. The outcomes will contribute new knowledge regarding dynamic visual processing and the ageing visual system and will inform vision testing, potential interventions to improve visual function for night driving and reduce the dangers of night driving.Read moreRead less
Neural plasticity in older adult human vision. This project aims to expand our understanding of age related changes in brain function, specifically plasticity. The project will increase knowledge of the role of an inhibitory neurotransmitter GABA in visual plasticity. Expected outcomes include new knowledge regarding the regulation of brain function in adulthood, enabling future research and planning for societal benefit to older Australia.
Design and Analysis of Optimal Algorithms for Automated Perimetry. Australian demographic studies reveal that visual impairment contributes significantly to disability in the elderly. Glaucoma, the second leading cause of blindness in developed nations, may be slowed if detected early, however recent studies estimate 50% of Australians with glaucoma are undiagnosed. Automated perimetry is used to detect and track such vision loss, but perimetry algorithms perform poorly. This project will design ....Design and Analysis of Optimal Algorithms for Automated Perimetry. Australian demographic studies reveal that visual impairment contributes significantly to disability in the elderly. Glaucoma, the second leading cause of blindness in developed nations, may be slowed if detected early, however recent studies estimate 50% of Australians with glaucoma are undiagnosed. Automated perimetry is used to detect and track such vision loss, but perimetry algorithms perform poorly. This project will design and analyse new algorithms with superior accuracy and efficiency, improving detection and monitoring of vision loss. Enhanced tools for community vision screening will also result, crucial for the ARC's priority goals of ?ageing well, ageing productively? and ?preventative healthcare?Read moreRead less
Shape4D: Modelling the Spatiotemporal Deformation Patterns in 3D Shapes. This research will develop new mathematical methods and algorithms that will enable the use of population-level longitudinal studies to model the spatial and temporal deformation patterns in 3D biological objects. Using novel geometric and deep learning techniques, it will create new methods that will allow the characterization of how the 3D shape of objects deforms with ageing, disease progression and interaction with thei ....Shape4D: Modelling the Spatiotemporal Deformation Patterns in 3D Shapes. This research will develop new mathematical methods and algorithms that will enable the use of population-level longitudinal studies to model the spatial and temporal deformation patterns in 3D biological objects. Using novel geometric and deep learning techniques, it will create new methods that will allow the characterization of how the 3D shape of objects deforms with ageing, disease progression and interaction with their environment, and the simulation of spatiotemporal deformations in anatomical organs. Benefits include a better understanding of growth processes, predictive models of how degenerative diseases progress and a computational framework that will assist in designing proper mitigation and intervention strategies.Read moreRead less
Optimal Robust Fitting under the Framework of LP-Type Problems. The project aims to develop algorithms to support the development of robust and accurate computer vision systems. Real-world visual data (images, videos) is inherently noisy and outlier prone. To build computer vision systems that work reliably in the real world, it is necessary to ensure that the underlying algorithms are robust and efficient. The project aims to devise novel algorithms that can compute the best possible result giv ....Optimal Robust Fitting under the Framework of LP-Type Problems. The project aims to develop algorithms to support the development of robust and accurate computer vision systems. Real-world visual data (images, videos) is inherently noisy and outlier prone. To build computer vision systems that work reliably in the real world, it is necessary to ensure that the underlying algorithms are robust and efficient. The project aims to devise novel algorithms that can compute the best possible result given the input data in a short amount of time. The expected outcomes would support the construction of reliable and accurate computer vision-based systems, such as large-scale 3-D reconstruction from photo collections, self-driving cars and domestic robots.Read moreRead less
Active multispectral computer vision for defence and security. This project will develop new techniques to extract intelligent information from multispectral images in the visible and near infra-red spectrum. It will enable computers to automatically recognise objects, faces and human actions with unprecedented accuracy.
Surviving the data deluge: Scalable feature extraction, discrimination and analysis for computer vision tasks using compressed sensed data. Strategically, our pioneering solutions besides being technically and socially significant, open fresh options for sensor-agnostic data analysis. The technical significance lies through the creation of new technologies for the critical national and global security markets, currently overwhelmed by data. The social significance arises from our solutions being ....Surviving the data deluge: Scalable feature extraction, discrimination and analysis for computer vision tasks using compressed sensed data. Strategically, our pioneering solutions besides being technically and socially significant, open fresh options for sensor-agnostic data analysis. The technical significance lies through the creation of new technologies for the critical national and global security markets, currently overwhelmed by data. The social significance arises from our solutions being privacy preserving, providing new avenues for the production of novel, socially acceptable products for aged care monitoring. Our methods spearhead future advancement in diverse disciplines due to the wide applicability of the methods to other sensor networks (Square Kilometre Array) and data types, providing new frameworks for addressing crucial problems of data management. Read moreRead less
Person identification from multiple non-invasive iris and face biometrics in video. This project will undertake research to develop a prototype system for personal identification that can be used by law enforcement and security agencies to enrol people at points of entry at public places. The system will non-invasively acquire face and iris biometrics and match them against a database of known persons. The proposed system can be used in sensitive buildings for access control, eliminating the nee ....Person identification from multiple non-invasive iris and face biometrics in video. This project will undertake research to develop a prototype system for personal identification that can be used by law enforcement and security agencies to enrol people at points of entry at public places. The system will non-invasively acquire face and iris biometrics and match them against a database of known persons. The proposed system can be used in sensitive buildings for access control, eliminating the need to carry access cards or remember passwords. This research contributes to the national research priority of Safeguarding Australia. We will develop new techniques in computer vision and train new researchers in this area.Read moreRead less
Human visual determination of shape. Visual coding of shape is central to our ability to interact with objects effectively. The visual system contains processes that are specific to particular shapes and this work aims to determine how those processes are used by the system in visual analysis. The work will advance theoretical understanding, and will contribute to the training of the next generation of researchers but also has the potential to provide information that enables display designers ....Human visual determination of shape. Visual coding of shape is central to our ability to interact with objects effectively. The visual system contains processes that are specific to particular shapes and this work aims to determine how those processes are used by the system in visual analysis. The work will advance theoretical understanding, and will contribute to the training of the next generation of researchers but also has the potential to provide information that enables display designers to determine the most efficient way to detect and present pattern information. This may lead to simplified methods for creating objects that are equally effective in conveying information and more rapid scene analysis. Read moreRead less